{"adoption": {"forks": 173, "observed_at": "2026-08-28T04:04:32.813986+00:00", "stars": 1373}, "canonical_url": "https://ross.abutalabs.com/products/cascalog", "card": {"archived": false, "artifact_type": "library", "description": "Data processing on Hadoop without the hassle.", "domain": ["big-data"], "enriched": true, "function": ["etl", "data-science"], "health_score": 20, "homepage": null, "language": "Clojure", "license": "NOASSERTION", "license_family": "other", "maturity": "maintenance", "member_repos": ["nathanmarz/cascalog"], "name": "nathanmarz/cascalog", "platform": ["jvm", "jvm-scripting"], "pushed_at": "2023-05-18T22:49:55+00:00", "repo": "nathanmarz/cascalog", "stars": 1373, "tags": ["hadoop", "datalog", "clojure", "big-data", "mapreduce", "query", "data-engineering"], "topics": [], "urls": [], "use_cases": ["run big data queries on hadoop without writing mapreduce", "replace pig or hive with a clojure dsl", "analyze datasets locally from the repl", "process large log data with clojure", "write declarative data pipelines in java"], "what_it_is": "Cascalog is a Clojure/Java data processing and querying library built on Hadoop, offering a high-level Datalog-like abstraction as a replacement for Pig, Hive, and Cascading. It also supports local in-memory analysis from the REPL.", "when_to_avoid": ["starting a new project — modern alternatives like Spark or trino are actively maintained", "you need non-Hadoop distributed execution"], "when_to_choose": ["you're on the JVM and want a high-level query language over Hadoop", "you prefer Clojure REPL-driven data analysis"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/cascalog", "repo": "nathanmarz/cascalog", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:32.813986+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:40:43.024389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8f7d197e074618bdd77f8b6768067c3acd272b5ed6c38c732caf67dabc8505ad", "fetched_at": "2026-08-28T04:04:32.813986+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nathanmarz/cascalog"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:32.813986+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:40:43.024389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8f7d197e074618bdd77f8b6768067c3acd272b5ed6c38c732caf67dabc8505ad", "fetched_at": "2026-08-28T04:04:32.813986+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nathanmarz/cascalog"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:40:43.024389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8f7d197e074618bdd77f8b6768067c3acd272b5ed6c38c732caf67dabc8505ad", "fetched_at": "2026-08-28T04:04:32.813986+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nathanmarz/cascalog"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:32.813986+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:32.813986+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:32.813986+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:40:43.024389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8f7d197e074618bdd77f8b6768067c3acd272b5ed6c38c732caf67dabc8505ad", "fetched_at": "2026-08-28T04:04:32.813986+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nathanmarz/cascalog"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:32.813986+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:32.813986+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:40:43.024389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8f7d197e074618bdd77f8b6768067c3acd272b5ed6c38c732caf67dabc8505ad", "fetched_at": "2026-08-28T04:04:32.813986+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nathanmarz/cascalog"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:32.813986+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:32.813986+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:32.813986+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:40:43.024389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8f7d197e074618bdd77f8b6768067c3acd272b5ed6c38c732caf67dabc8505ad", "fetched_at": "2026-08-28T04:04:32.813986+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nathanmarz/cascalog"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:32.813986+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:32.813986+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:40:43.024389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8f7d197e074618bdd77f8b6768067c3acd272b5ed6c38c732caf67dabc8505ad", "fetched_at": "2026-08-28T04:04:32.813986+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nathanmarz/cascalog"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:40:43.024389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8f7d197e074618bdd77f8b6768067c3acd272b5ed6c38c732caf67dabc8505ad", "fetched_at": "2026-08-28T04:04:32.813986+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nathanmarz/cascalog"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:40:43.024389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8f7d197e074618bdd77f8b6768067c3acd272b5ed6c38c732caf67dabc8505ad", "fetched_at": "2026-08-28T04:04:32.813986+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nathanmarz/cascalog"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:40:43.024389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8f7d197e074618bdd77f8b6768067c3acd272b5ed6c38c732caf67dabc8505ad", "fetched_at": "2026-08-28T04:04:32.813986+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nathanmarz/cascalog"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 6000, "days_push": 1203, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}